Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    say hist

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Y
    -0.07
    Statistics
    -0.07
    Walking
    -0.07
    Collider
    -0.07
    .defaults
    -0.07
    ptides
    -0.06
    itting
    -0.06
     flowering
    -0.06
    pty
    -0.06
    添加
    -0.06
    POSITIVE LOGITS
     gec
    0.07
     الاع
    0.07
     зад
    0.06
     ServletException
    0.06
    �
    0.06
    ."',
    0.06
    enis
    0.06
     mue
    0.06
    osloven
    0.06
     Masc
    0.06
    Act Density 0.003%

    No Known Activations